2021-04-26 13:58:18 +08:00
|
|
|
|
<div align="center">
|
|
|
|
|
|
2022-01-22 10:36:39 +08:00
|
|
|
|
<img src="resources/mmcls-logo.png" width="600"/>
|
|
|
|
|
<div> </div>
|
|
|
|
|
<div align="center">
|
|
|
|
|
<b><font size="5">OpenMMLab 官网</font></b>
|
|
|
|
|
<sup>
|
|
|
|
|
<a href="https://openmmlab.com">
|
|
|
|
|
<i><font size="4">HOT</font></i>
|
|
|
|
|
</a>
|
|
|
|
|
</sup>
|
|
|
|
|
|
|
|
|
|
<b><font size="5">OpenMMLab 开放平台</font></b>
|
|
|
|
|
<sup>
|
|
|
|
|
<a href="https://platform.openmmlab.com">
|
|
|
|
|
<i><font size="4">TRY IT OUT</font></i>
|
|
|
|
|
</a>
|
|
|
|
|
</sup>
|
|
|
|
|
</div>
|
|
|
|
|
<div> </div>
|
|
|
|
|
|
|
|
|
|
[](https://pypi.org/project/mmcls)
|
|
|
|
|
[](https://mmclassification.readthedocs.io/zh_CN/latest/)
|
|
|
|
|
[](https://github.com/open-mmlab/mmclassification/actions)
|
|
|
|
|
[](https://codecov.io/gh/open-mmlab/mmclassification)
|
|
|
|
|
[](https://github.com/open-mmlab/mmclassification/blob/master/LICENSE)
|
|
|
|
|
[](https://github.com/open-mmlab/mmclassification/issues)
|
|
|
|
|
[](https://github.com/open-mmlab/mmclassification/issues)
|
|
|
|
|
|
|
|
|
|
[📘 中文文档](https://mmclassification.readthedocs.io/zh_CN/latest/) |
|
|
|
|
|
[🛠️ 安装教程](https://mmclassification.readthedocs.io/zh_CN/latest/install.html) |
|
|
|
|
|
[👀 模型库](https://mmclassification.readthedocs.io/zh_CN/latest/model_zoo.html) |
|
|
|
|
|
[🆕 更新日志](https://mmclassification.readthedocs.io/en/latest/changelog.html) |
|
|
|
|
|
[🤔 报告问题](https://github.com/open-mmlab/mmclassification/issues/new/choose)
|
2021-04-26 13:58:18 +08:00
|
|
|
|
|
2022-01-22 10:36:39 +08:00
|
|
|
|
</div>
|
2021-04-26 13:58:18 +08:00
|
|
|
|
|
|
|
|
|
## Introduction
|
|
|
|
|
|
2022-01-22 10:36:39 +08:00
|
|
|
|
[English](/README.md) | 简体中文
|
|
|
|
|
|
2021-06-03 16:49:53 +08:00
|
|
|
|
MMClassification 是一款基于 PyTorch 的开源图像分类工具箱,是 [OpenMMLab](https://openmmlab.com/) 项目的成员之一
|
2021-04-26 13:58:18 +08:00
|
|
|
|
|
2022-01-22 10:36:39 +08:00
|
|
|
|
主分支代码目前支持 PyTorch 1.5 以上的版本。
|
2021-04-26 13:58:18 +08:00
|
|
|
|
|
2022-01-22 10:36:39 +08:00
|
|
|
|
<div align="center">
|
|
|
|
|
<img src="https://user-images.githubusercontent.com/9102141/87268895-3e0d0780-c4fe-11ea-849e-6140b7e0d4de.gif" width="70%"/>
|
|
|
|
|
</div>
|
2021-04-26 13:58:18 +08:00
|
|
|
|
|
|
|
|
|
### 主要特性
|
|
|
|
|
|
|
|
|
|
- 支持多样的主干网络与预训练模型
|
|
|
|
|
- 支持配置多种训练技巧
|
|
|
|
|
- 大量的训练配置文件
|
|
|
|
|
- 高效率和高可扩展性
|
2021-12-31 12:55:47 +08:00
|
|
|
|
- 功能强大的工具箱
|
2021-04-26 13:58:18 +08:00
|
|
|
|
|
|
|
|
|
## 更新日志
|
|
|
|
|
|
2022-01-31 11:51:49 +08:00
|
|
|
|
2022/1/30 发布了 v0.20.0 版本
|
|
|
|
|
|
|
|
|
|
新版本亮点:
|
|
|
|
|
- 支持 **K 折交叉验证** 工具。相应文档会在后续添加。
|
|
|
|
|
- 支持了 **HRNet**,**ConvNeXt**,**Twins** 以及 **EfficientNet** 四个主干网络,欢迎使用!
|
|
|
|
|
- 支持了从 PyTorch 模型到 Core-ML 模型的转换工具。
|
|
|
|
|
|
2021-12-31 12:55:47 +08:00
|
|
|
|
2021/12/31 发布了 v0.19.0 版本
|
|
|
|
|
|
|
|
|
|
新版本亮点:
|
|
|
|
|
- **特征提取**功能得到了加强。详见 [#593](https://github.com/open-mmlab/mmclassification/pull/593)。
|
|
|
|
|
- 提供了 **ResNet-50** 的高精度训练配置,原论文参见 [*ResNet strikes back*](https://arxiv.org/abs/2110.00476)。
|
|
|
|
|
- 复现了 **T2T-ViT** 和 **RegNetX** 的训练精度,并提供了自训练的模型权重文件。
|
|
|
|
|
- 支持了 **DeiT** 和 **Conformer** 主干网络,并提供了预训练模型。
|
|
|
|
|
- 提供了一个 **CAM 可视化** 工具。该工具基于 [pytorch-grad-cam](https://github.com/jacobgil/pytorch-grad-cam),我们提供了详细的 [使用教程](https://mmclassification.readthedocs.io/en/latest/tools/visualization.html#class-activation-map-visualization)!
|
|
|
|
|
|
2021-12-15 10:34:34 +08:00
|
|
|
|
发布历史和更新细节请参考 [更新日志](docs/en/changelog.md)
|
2021-04-26 13:58:18 +08:00
|
|
|
|
|
2022-01-22 10:36:39 +08:00
|
|
|
|
## 安装
|
|
|
|
|
|
|
|
|
|
请参考 [安装指南](https://mmclassification.readthedocs.io/zh_CN/latest/install.html) 进行安装
|
|
|
|
|
|
|
|
|
|
## 基础教程
|
|
|
|
|
|
|
|
|
|
请参考 [基础教程](https://mmclassification.readthedocs.io/zh_CN/latest/getting_started.html) 来了解 MMClassification 的基本使用。MMClassification 也提供了其他更详细的教程:
|
|
|
|
|
|
|
|
|
|
- [如何编写配置文件](https://mmclassification.readthedocs.io/zh_CN/latest/tutorials/config.html)
|
|
|
|
|
- [如何微调模型](https://mmclassification.readthedocs.io/zh_CN/latest/tutorials/finetune.html)
|
|
|
|
|
- [如何增加新数据集](https://mmclassification.readthedocs.io/zh_CN/latest/tutorials/new_dataset.html)
|
|
|
|
|
- [如何设计数据处理流程](https://mmclassification.readthedocs.io/zh_CN/latest/tutorials/data_pipeline.html)
|
|
|
|
|
- [如何增加新模块](https://mmclassification.readthedocs.io/zh_CN/latest/tutorials/new_modules.html)
|
|
|
|
|
- [如何自定义优化策略](https://mmclassification.readthedocs.io/zh_CN/latest/tutorials/schedule.html)
|
|
|
|
|
- [如何自定义运行参数](https://mmclassification.readthedocs.io/zh_CN/latest/tutorials/runtime.html)
|
|
|
|
|
|
|
|
|
|
我们也提供了相应的中文 Colab 教程:
|
|
|
|
|
|
|
|
|
|
- 了解 MMClassification **Python API**:[预览 Notebook](https://github.com/open-mmlab/mmclassification/blob/master/docs/zh_CN/tutorials/MMClassification_python_cn.ipynb) 或者直接[在 Colab 上运行](https://colab.research.google.com/github/open-mmlab/mmclassification/blob/master/docs/zh_CN/tutorials/MMClassification_python_cn.ipynb)。
|
|
|
|
|
- 了解 MMClassification **命令行工具**:[预览 Notebook](https://github.com/open-mmlab/mmclassification/blob/master/docs/zh_CN/tutorials/MMClassification_tools_cn.ipynb) 或者直接[在 Colab 上运行](https://colab.research.google.com/github/open-mmlab/mmclassification/blob/master/docs/zh_CN/tutorials/MMClassification_tools_cn.ipynb)。
|
|
|
|
|
|
|
|
|
|
## 模型库
|
2021-04-26 13:58:18 +08:00
|
|
|
|
|
2022-01-04 11:38:05 +08:00
|
|
|
|
相关结果和模型可在 [model zoo](https://mmclassification.readthedocs.io/en/latest/model_zoo.html) 中获得
|
2021-04-26 13:58:18 +08:00
|
|
|
|
|
2021-12-31 12:55:47 +08:00
|
|
|
|
<details open>
|
|
|
|
|
<summary>支持的主干网络</summary>
|
|
|
|
|
|
|
|
|
|
- [x] [VGG](https://github.com/open-mmlab/mmclassification/tree/master/configs/vgg)
|
|
|
|
|
- [x] [ResNet](https://github.com/open-mmlab/mmclassification/tree/master/configs/resnet)
|
|
|
|
|
- [x] [ResNeXt](https://github.com/open-mmlab/mmclassification/tree/master/configs/resnext)
|
|
|
|
|
- [x] [SE-ResNet](https://github.com/open-mmlab/mmclassification/tree/master/configs/seresnet)
|
|
|
|
|
- [x] [SE-ResNeXt](https://github.com/open-mmlab/mmclassification/tree/master/configs/seresnet)
|
|
|
|
|
- [x] [RegNet](https://github.com/open-mmlab/mmclassification/tree/master/configs/repvgg)
|
|
|
|
|
- [x] [ShuffleNetV1](https://github.com/open-mmlab/mmclassification/tree/master/configs/shufflenet_v1)
|
|
|
|
|
- [x] [ShuffleNetV2](https://github.com/open-mmlab/mmclassification/tree/master/configs/shufflenet_v2)
|
|
|
|
|
- [x] [MobileNetV2](https://github.com/open-mmlab/mmclassification/tree/master/configs/mobilenet_v2)
|
|
|
|
|
- [x] [MobileNetV3](https://github.com/open-mmlab/mmclassification/tree/master/configs/mobilenet_v3)
|
|
|
|
|
- [x] [Swin-Transformer](https://github.com/open-mmlab/mmclassification/tree/master/configs/swin_transformer)
|
|
|
|
|
- [x] [RepVGG](https://github.com/open-mmlab/mmclassification/tree/master/configs/repvgg)
|
|
|
|
|
- [x] [Vision-Transformer](https://github.com/open-mmlab/mmclassification/tree/master/configs/vision_transformer)
|
|
|
|
|
- [x] [Transformer-in-Transformer](https://github.com/open-mmlab/mmclassification/tree/master/configs/tnt)
|
|
|
|
|
- [x] [Res2Net](https://github.com/open-mmlab/mmclassification/tree/master/configs/res2net)
|
|
|
|
|
- [x] [MLP-Mixer](https://github.com/open-mmlab/mmclassification/tree/master/configs/mlp_mixer)
|
|
|
|
|
- [x] [DeiT](https://github.com/open-mmlab/mmclassification/tree/master/configs/deit)
|
|
|
|
|
- [x] [Conformer](https://github.com/open-mmlab/mmclassification/tree/master/configs/conformer)
|
|
|
|
|
- [x] [T2T-ViT](https://github.com/open-mmlab/mmclassification/tree/master/configs/t2t_vit)
|
2022-01-28 10:36:45 +08:00
|
|
|
|
- [x] [Twins](https://github.com/open-mmlab/mmclassification/tree/master/configs/twins)
|
|
|
|
|
- [x] [EfficientNet](https://github.com/open-mmlab/mmclassification/tree/master/configs/efficientnet)
|
|
|
|
|
- [x] [ConvNeXt](https://github.com/open-mmlab/mmclassification/tree/master/configs/convnext)
|
2022-01-28 10:54:14 +08:00
|
|
|
|
- [x] [HRNet](https://github.com/open-mmlab/mmclassification/tree/master/configs/hrnet)
|
2021-12-31 12:55:47 +08:00
|
|
|
|
|
|
|
|
|
</details>
|
2021-04-26 13:58:18 +08:00
|
|
|
|
|
|
|
|
|
## 参与贡献
|
|
|
|
|
|
2022-01-04 11:38:05 +08:00
|
|
|
|
我们非常欢迎任何有助于提升 MMClassification 的贡献,请参考 [贡献指南](https://mmclassification.readthedocs.io/zh_CN/latest/community/CONTRIBUTING.html) 来了解如何参与贡献。
|
2021-04-26 13:58:18 +08:00
|
|
|
|
|
|
|
|
|
## 致谢
|
|
|
|
|
|
|
|
|
|
MMClassification 是一款由不同学校和公司共同贡献的开源项目。我们感谢所有为项目提供算法复现和新功能支持的贡献者,以及提供宝贵反馈的用户。
|
|
|
|
|
|
|
|
|
|
我们希望该工具箱和基准测试可以为社区提供灵活的代码工具,供用户复现现有算法并开发自己的新模型,从而不断为开源社区提供贡献。
|
|
|
|
|
|
2022-01-22 10:36:39 +08:00
|
|
|
|
## 引用
|
|
|
|
|
|
|
|
|
|
如果你在研究中使用了本项目的代码或者性能基准,请参考如下 bibtex 引用 MMClassification。
|
|
|
|
|
|
|
|
|
|
```BibTeX
|
|
|
|
|
@misc{2020mmclassification,
|
|
|
|
|
title={OpenMMLab's Image Classification Toolbox and Benchmark},
|
|
|
|
|
author={MMClassification Contributors},
|
|
|
|
|
howpublished = {\url{https://github.com/open-mmlab/mmclassification}},
|
|
|
|
|
year={2020}
|
|
|
|
|
}
|
|
|
|
|
```
|
|
|
|
|
|
|
|
|
|
## 许可证
|
|
|
|
|
|
|
|
|
|
该项目开源自 [Apache 2.0 license](LICENSE).
|
|
|
|
|
|
2021-04-26 13:58:18 +08:00
|
|
|
|
## OpenMMLab 的其他项目
|
|
|
|
|
|
|
|
|
|
- [MMCV](https://github.com/open-mmlab/mmcv): OpenMMLab 计算机视觉基础库
|
2021-07-27 17:58:04 +08:00
|
|
|
|
- [MIM](https://github.com/open-mmlab/mim): MIM 是 OpenMMlab 项目、算法、模型的统一入口
|
2021-04-26 13:58:18 +08:00
|
|
|
|
- [MMDetection](https://github.com/open-mmlab/mmdetection): OpenMMLab 检测工具箱与测试基准
|
2021-06-03 16:49:53 +08:00
|
|
|
|
- [MMDetection3D](https://github.com/open-mmlab/mmdetection3d): OpenMMLab 新一代通用 3D 目标检测平台
|
2021-04-26 13:58:18 +08:00
|
|
|
|
- [MMSegmentation](https://github.com/open-mmlab/mmsegmentation): OpenMMLab 语义分割工具箱与测试基准
|
|
|
|
|
- [MMAction2](https://github.com/open-mmlab/mmaction2): OpenMMLab 新一代视频理解工具箱与测试基准
|
|
|
|
|
- [MMTracking](https://github.com/open-mmlab/mmtracking): OpenMMLab 一体化视频目标感知平台
|
|
|
|
|
- [MMPose](https://github.com/open-mmlab/mmpose): OpenMMLab 姿态估计工具箱与测试基准
|
|
|
|
|
- [MMEditing](https://github.com/open-mmlab/mmediting): OpenMMLab 图像视频编辑工具箱
|
|
|
|
|
- [MMOCR](https://github.com/open-mmlab/mmocr): OpenMMLab 全流程文字检测识别理解工具包
|
|
|
|
|
- [MMGeneration](https://github.com/open-mmlab/mmgeneration): OpenMMLab 生成模型工具箱
|
2021-11-19 11:33:17 +08:00
|
|
|
|
- [MMFlow](https://github.com/open-mmlab/mmflow): OpenMMLab 光流估计工具箱与测试基准
|
2021-11-29 19:00:51 +08:00
|
|
|
|
- [MMFewShot](https://github.com/open-mmlab/mmfewshot): OpenMMLab 少样本学习工具箱与测试基准
|
2021-12-07 11:16:33 +08:00
|
|
|
|
- [MMHuman3D](https://github.com/open-mmlab/mmhuman3d):OpenMMLab 人体参数化模型工具箱与测试基准
|
2022-01-04 11:38:05 +08:00
|
|
|
|
- [MMSelfSup](https://github.com/open-mmlab/mmselfsup): OpenMMLab 自监督学习工具箱与测试基准
|
|
|
|
|
- [MMRazor](https://github.com/open-mmlab/mmrazor): OpenMMLab 模型压缩工具箱与测试基准
|
|
|
|
|
- [MMDeploy](https://github.com/open-mmlab/mmdeploy): OpenMMLab 模型部署框架
|
2021-04-26 13:58:18 +08:00
|
|
|
|
|
|
|
|
|
## 欢迎加入 OpenMMLab 社区
|
|
|
|
|
|
2022-01-22 10:36:39 +08:00
|
|
|
|
扫描下方的二维码可关注 OpenMMLab 团队的 [知乎官方账号](https://www.zhihu.com/people/openmmlab),加入 OpenMMLab 团队的 [官方交流 QQ 群](https://jq.qq.com/?_wv=1027&k=aCvMxdr3) 或联络 OpenMMLab 官方微信小助手
|
2021-04-26 13:58:18 +08:00
|
|
|
|
|
|
|
|
|
<div align="center">
|
2022-01-22 10:36:39 +08:00
|
|
|
|
<img src="https://github.com/open-mmlab/mmcv/raw/master/docs/en/_static/zhihu_qrcode.jpg" height="400" /> <img src="https://github.com/open-mmlab/mmcv/raw/master/docs/en/_static/qq_group_qrcode.jpg" height="400" /> <img src="https://github.com/open-mmlab/mmcv/raw/master/docs/en/_static/wechat_qrcode.jpg" height="400" />
|
2021-04-26 13:58:18 +08:00
|
|
|
|
</div>
|
|
|
|
|
|
|
|
|
|
我们会在 OpenMMLab 社区为大家
|
|
|
|
|
|
|
|
|
|
- 📢 分享 AI 框架的前沿核心技术
|
|
|
|
|
- 💻 解读 PyTorch 常用模块源码
|
|
|
|
|
- 📰 发布 OpenMMLab 的相关新闻
|
|
|
|
|
- 🚀 介绍 OpenMMLab 开发的前沿算法
|
|
|
|
|
- 🏃 获取更高效的问题答疑和意见反馈
|
|
|
|
|
- 🔥 提供与各行各业开发者充分交流的平台
|
|
|
|
|
|
|
|
|
|
干货满满 📘,等你来撩 💗,OpenMMLab 社区期待您的加入 👬
|